Fieldops prompt refiner
Transforms rough, ambiguous, overloaded, or reusable requests into precise, execution-ready prompts for coding agents. Use when asked to improve, rewrite, refine, tighten, structure, modularize, audit, or professionalize a prompt, AGENTS.md instruction set, task brief, system prompt, or agent workflow. Preserves intent while clarifying outcome, scope, inputs, constraints, authority, verification, and deliverables. Does not apply when merely executing an already well-specified task.From its SKILL.md
npx -y skills add download4you/n2-fieldops --skill fieldops-prompt-refinerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, 142 tokens by cl100k_base, as published. Nobody here has run it
Prompt Refiner
- Extract outcome, audience/agent, inputs, environment, and completion condition.
- Separate hard constraints from preferences and examples.
- Ask only about ambiguities that materially change safe execution.
- Remove duplication, conflict, unenforceable claims, and low-value prose.
- Organize with
references/prompt-architecture.md. - Add proportional evidence and verification requirements.
- Preserve language, terminology, intent, and authority boundary.
- Return a copy-ready prompt plus a short design note when useful.
For large reusable profiles, prefer modular skills and references over one always-loaded prompt. Never claim a prompt can override higher-priority runtime instructions.
What ships with it: 2 files
629 B alongside SKILL.md
agents/
- openai.yaml227 B